Generative AI in Production

Generative AI in ProductionGAIPGOGoogleGO-GAIP2.0<ul> <li>Understand the challenges in productionizing applications using generative AI</li><li>Manage experimentation and evaluation for LLM-powered application</li><li>Productionize LLM-powered applications</li><li>Secure generative AI applications</li><li>Implement logging and monitoring for LLM-powered applications</li></ul>Completion of <a class="fl-href-prod" href="/swisscom/fr/course/google-adlgc"><svg role="img" aria-hidden="true" focusable="false" data-nosnippet class="cms-linkmark"><use xlink:href="/css/img/icnset-linkmarks.svg#linkmark"></use></svg>Application Development with LLMs on Google Cloud (ADLGC)</a> or equivalent knowledge.Developers, DevOps engineers and machine learning engineers who wish to operationalize GenAI-based applications<h4>Module 1 - Introduction to Generative AI in Production</h4> Topics: <ul> <li>Generative AI Operations</li><li>Traditional MLOps vs. GenAIOps</li><li>Components of an LLM System</li><li>RAG/ReAct architecture</li></ul>Objectives: <ul> <li>Understand generative AI operations</li><li>Compare traditional MLOps and GenAIOps</li><li>Analyze the components of an LLM system</li><li>Define and compare RAG and ReAct</li></ul><h4>Module 2 - Generative AI Application Deployment</h4> Topics: <ul> <li>Application deployment options</li><li>Deployment, packaging, and versioning</li></ul>Objectives: <ul> <li>Evaluate application deployment options</li><li>Deploy, package, and version apps</li></ul>Activities: <ul> <li>Lab: Deploying an Agentic Application on Cloud Run</li></ul><h4>Module 3 - Productionizing Generative AI</h4> Topics: <ul> <li>Maintenance and updates</li><li>Testing and evaluation</li><li>CI/CD pipelines for gen AI-powered apps</li></ul>Objectives: <ul> <li>Maintain and update LLM models</li><li>Test and evaluate gen AI-powered apps</li><li>Deploy CI/CD pipelines for gen AI-powered apps</li></ul>Activities: <ul> <li>Lab: Tracking Versions of Generative AI Applications</li></ul><h4>Module 4 - Securing Generative AI Applications</h4> Topics: <ul> <li>Security challenges</li><li>Prompt security</li><li>Sensitive Data Protection and DLP API</li><li>Model Armor</li></ul>Objectives: <ul> <li>Identify security challenges for gen AI applications</li><li>Understand prompt security issues</li><li>Apply sensitive data protection and DLP API</li><li>Implement Model Armor</li></ul>Activities: <ul> <li>Lab: Securing Generative AI-Powered Applications</li></ul><h4>Module 5 - Observability for Production LLM Systems</h4> Topics: <ul> <li>Cloud Operations</li><li>Cloud Logging</li><li>Monitoring</li><li>Cloud Trace</li><li>Agent Analytics and AgentOps</li><li>Putting it all together</li></ul>Objectives: <ul> <li>Describe the purpose and capabilities of Google Cloud Observability</li><li>Explain the purpose of Cloud Monitoring</li><li>Explain the purpose of Cloud Logging</li><li>Explain the purpose of Cloud Trace</li></ul>Activities: <ul> <li>Lab: Logging, Monitoring, and Agent Analytics</li></ul>- Understand the challenges in productionizing applications using generative AI - Manage experimentation and evaluation for LLM-powered application - Productionize LLM-powered applications - Secure generative AI applications - Implement logging and monitoring for LLM-powered applicationsCompletion of Application Development with LLMs on Google Cloud (ADLGC) or equivalent knowledge.Developers, DevOps engineers and machine learning engineers who wish to operationalize GenAI-based applicationsModule 1 - Introduction to Generative AI in Production Topics: - Generative AI Operations - Traditional MLOps vs. GenAIOps - Components of an LLM System - RAG/ReAct architecture Objectives: - Understand generative AI operations - Compare traditional MLOps and GenAIOps - Analyze the components of an LLM system - Define and compare RAG and ReAct Module 2 - Generative AI Application Deployment Topics: - Application deployment options - Deployment, packaging, and versioning Objectives: - Evaluate application deployment options - Deploy, package, and version apps Activities: - Lab: Deploying an Agentic Application on Cloud Run Module 3 - Productionizing Generative AI Topics: - Maintenance and updates - Testing and evaluation - CI/CD pipelines for gen AI-powered apps Objectives: - Maintain and update LLM models - Test and evaluate gen AI-powered apps - Deploy CI/CD pipelines for gen AI-powered apps Activities: - Lab: Tracking Versions of Generative AI Applications Module 4 - Securing Generative AI Applications Topics: - Security challenges - Prompt security - Sensitive Data Protection and DLP API - Model Armor Objectives: - Identify security challenges for gen AI applications - Understand prompt security issues - Apply sensitive data protection and DLP API - Implement Model Armor Activities: - Lab: Securing Generative AI-Powered Applications Module 5 - Observability for Production LLM Systems Topics: - Cloud Operations - Cloud Logging - Monitoring - Cloud Trace - Agent Analytics and AgentOps - Putting it all together Objectives: - Describe the purpose and capabilities of Google Cloud Observability - Explain the purpose of Cloud Monitoring - Explain the purpose of Cloud Logging - Explain the purpose of Cloud Trace Activities: - Lab: Logging, Monitoring, and Agent Analytics1 jour595.00820.00660.00650.00950.00950.00950.00790.00950.00